Commits · 34348012d6b43eca5e241fe97381420d5758866c · nexedi / linux

25 Sep, 2006 14 commits

[ARM] 3800/2: S3C2412: DMA channel mappings · 34348012

Ben Dooks authored Sep 18, 2006

DMA channel mappings for the S3C2312
Signed-off-by: Ben Dooks <ben-linux@fluff.org>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>

34348012

[ARM] 3814/1: move 80200 dma_inv_range() erratum check out of line · 197c9444

Lennert Buytenhek authored Sep 16, 2006

On stepping A0/A1 of the 80200, invalidating D-cache by line doesn't
clear the dirty bits, which means that if we invalidate a dirty line,
the dirty data can still be written back to memory later on.

To work around this, dma_inv_range() on these two processors is
implemented as dma_flush_range() (i.e. do a clean D-cache line before
doing the invalidate D-cache line.) For this, we currently have a
processor ID check in xscale_dma_inv_range(), but a better solution
is to add a separate cache_fns and proc_info for A0/A1 80200.
Signed-off-by: Lennert Buytenhek <buytenh@wantstofly.org>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>

197c9444

[ARM] 3813/1: prevent >= 4G /dev/mem mmap() · 51635ad2

Lennert Buytenhek authored Sep 16, 2006

Prevent userland from mapping in physical address regions >= 4G by
checking for that in valid_mmap_phys_addr_range().

Unfortunately, we cannot override valid_mmap_phys_addr_range() without
also overriding valid_phys_addr_range(), so copy drivers/char/mem.c's
version of valid_phys_addr_range() over to arch/arm/mm/mmap.c as well.
Signed-off-by: Lennert Buytenhek <buytenh@wantstofly.org>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>

51635ad2

[ARM] 3811/1: ep93xx: add cirrus logic edb9312 support · bf11d26c

Lennert Buytenhek authored Sep 16, 2006

Add Cirrus Logic EDB9312 support.
Signed-off-by: Lennert Buytenhek <buytenh@wantstofly.org>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>

bf11d26c

[ARM] 3810/1: switch atomic helpers over to raw_local_irq_{save,restore} · 8dd5c845

Lennert Buytenhek authored Sep 16, 2006

Now that we have raw_* variants of local_irq_$FOO(), switch the atomic
helpers over to use those raw_* variants.  This is necessary when using
lockdep on pre-ARMv6 hardware, as lockdep uses atomic_t counters in the
trace_hardirqs_off() path.
Signed-off-by: Lennert Buytenhek <buytenh@wantstofly.org>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>

8dd5c845

[ARM] 3805/1: S3C2412: LCD register update · 34148c69

Ben Dooks authored Sep 16, 2006

Add LCD register definitions for the S3C2412.
Signed-off-by: Ben Dooks <ben-linux@fluff.org>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>

34148c69

[ARM] 3804/1: S3C2442: LCD register update · 3e9fc8e5

Ben Dooks authored Sep 16, 2006

Add LCD register definitions for the S3C2442.
Signed-off-by: Ben Dooks <ben-linux@fluff.org>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>

3e9fc8e5

[ARM] 3802/1: S3C24XX: PM tidy up cache flushing · 58095d7f

Ben Dooks authored Sep 16, 2006

Change to using flush_cache_all() in pm.c and
also remove the need to flush the cache in the
PM code.

This changes the sleep.S code to have an entry
to store the registers for resume, and then a
second entry (after the caches are cleaned)
to do the suspend and resume.
Signed-off-by: Ben Dooks <ben-linux@fluff.org>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>

58095d7f

[ARM] 3801/1: S3C24XX: Move IRQ PM out of pm.c · 1e582fc7

Ben Dooks authored Sep 16, 2006

Seperate the IRQ power management code out of
the pm.c file, and add it to the relevant
system class devices.

Also make the suspend and resume code take
notice of the fact these registers can be
moved by compile time code.

Add fix from Ilya Yanok to also save the
INTSUBMSK over sleep.
Signed-off-by: Ben Dooks <ben-linux@fluff.org>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>

1e582fc7

[ARM] 3799/1: S3C2442: DMA channel mappings · 3fc3a25b